Micro-Data Reinforcement Learning for Adaptive Robots

Autor: Chatzilygeroudis, Konstantinos

Les robots opèrent dans le monde réel, dans lequel essayer quelque chose prend beaucoup de temps. Pourtant, les methodes d’apprentissage par renforcement actuels (par exemple, deep reinforcement learning) nécessitent de longues périodes d�

Externí odkaz: http://www.theses.fr/2018LORR0276/document

A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials

Autor: Konstantinos Chatzilygeroudis, Vassilis Vassiliades, Freek Stulp, Sylvain Calinon, Jean-Baptiste Mouret

Publikováno v: IEEE Transactions on Robotics
IEEE Transactions on Robotics, IEEE, 2020, 36 (2), pp.328-347. ⟨10.1109/TRO.2019.2958211⟩
IEEE Transactions on Robotics, IEEE, In press, ⟨10.1109/TRO.2019.2958211⟩
IEEE Transactions on Robotics, 2020, 36 (2), pp.328-347. ⟨10.1109/TRO.2019.2958211⟩

Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt with only a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8f2ae2bfaca17d09adfe29fa774b06e